© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9606
    Prev
    Next
    INDEX
    Explanations

    the word "field" in code or code-like text and properties in PHP

    oai_token-act-pair · gemini-2.0-flash

    Code function calls

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bezeichneter
    -0.63
     Chriſt
    -0.62
    ),"
    -0.58
    曖昧さ回避
    -0.58
    ioutil
    -0.57
     [];
    -0.57
     BoxFit
    -0.57
    urto
    -0.57
    Географија
    -0.57
     Forumite
    -0.57
    POSITIVE LOGITS
    enumi
    0.58
     kasarigan
    0.56
     JpaRepository
    0.54
    webElement
    0.52
    Enllaces
    0.51
     Toxicol
    0.44
    تقاوى
    0.43
    MockBean
    0.42
    KeyListener
    0.42
     médicale
    0.41
    Activations Density 0.509%

    No Known Activations